Geekbench ML Score

5229
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 15 2024 03:22 PM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPad14,4
Model IDiPad14,4
Motherboard J618AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.49 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.33 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3378
632.1 IPS
 
Image Classification (F16)
100% 3427
641.3 IPS
 
Image Classification (I8)
99% 3057
572.0 IPS
 
Image Segmentation (F32)
100% 1446
24.2 IPS
 
Image Segmentation (F16)
100% 1535
25.6 IPS
 
Image Segmentation (I8)
100% 1539
25.7 IPS
 
Pose Estimation (F32)
100% 23529
28.5 IPS
 
Pose Estimation (F16)
100% 24978
30.2 IPS
 
Pose Estimation (I8)
100% 24411
29.6 IPS
 
Object Detection (F32)
100% 2840
212.0 IPS
 
Object Detection (F16)
100% 2846
212.5 IPS
 
Object Detection (I8)
97% 2589
193.3 IPS
 
Face Detection (F32)
100% 9306
110.7 IPS
 
Face Detection (F16)
98% 10562
125.6 IPS
 
Face Detection (I8)
97% 10101
120.1 IPS
 
Depth Estimation (F32)
100% 16393
127.1 IPS
 
Depth Estimation (F16)
100% 17456
135.4 IPS
 
Depth Estimation (I8)
37% 16129
125.1 IPS
 
Style Transfer (F32)
100% 37662
49.5 IPS
 
Style Transfer (F16)
100% 46888
61.7 IPS
 
Style Transfer (I8)
100% 43300
57.0 IPS
 
Image Super-Resolution (F32)
100% 9406
335.9 IPS
 
Image Super-Resolution (F16)
100% 10192
364.0 IPS
 
Image Super-Resolution (I8)
100% 9769
348.9 IPS
 
Text Classification (F32)
100% 1121
1.61 KIPS
 
Text Classification (F16)
100% 744
1.07 KIPS
 
Text Classification (I8)
96% 744
1.07 KIPS
 
Machine Translation (F32)
100% 806
14.8 IPS
 
Machine Translation (F16)
100% 810
14.9 IPS
 
Machine Translation (I8)
99% 743
13.7 IPS
 

Compare

Set Baseline Geekbench 6 now available